Cover Image

Spatial variations prediction in carbonate porosity using artificial neural network: Subis Limestones, Sarawak, Malaysia

The estimation and modeling of carbonate porosity is of increasing interest in different aspects of geology. Several models have been developed to visualize the pore network systems of carbonate rocks. However, no modeling tools have been designed to predict changes in pore system resulting from dis...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali, Y., Padmanabhan, E., Andriamihaja, S., Faisal, A.
Format: Article
Published: Springer Nature 2019
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108113955&doi=10.1007%2f978-3-030-01440-7_44&partnerID=40&md5=bba797a117cea58f17fce9d057e445c5
http://eprints.utp.edu.my/23485/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.23485
record_format eprints
spelling my.utp.eprints.234852021-08-19T07:39:38Z Spatial variations prediction in carbonate porosity using artificial neural network: Subis Limestones, Sarawak, Malaysia Ali, Y. Padmanabhan, E. Andriamihaja, S. Faisal, A. The estimation and modeling of carbonate porosity is of increasing interest in different aspects of geology. Several models have been developed to visualize the pore network systems of carbonate rocks. However, no modeling tools have been designed to predict changes in pore system resulting from dissolution. Therefore, this paper introduced an algorithm for predicting spatial variations in pore network. Carbonate outcropped samples representing different facies from Subis limestone, Sarawak, of Miocene age were used for this study. Continuous imagery along a 10 cm rock chip was conducted using Micro Computer Tomography (CT) scan imagery. The Artificial Neural Network (ANN) predictive code receives images which were read as a matrix. The images were processed using the Image Analysis, coded before use as a training and input data set for ANN. The ANN produced a predicted image with the same properties (such as bits, scalar or raster etc.) as the input images and at the same interval. The predicted image was compared to the original one to estimate the prediction accuracy. The method proved to give good results in terms of the predicted images accuracy. The method can be applied to study the dissolution phenomenon in carbonates as well as siliciclastic rocks to predict spatial variations and development in a pore network system. © Springer Nature Switzerland AG 2019. Springer Nature 2019 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108113955&doi=10.1007%2f978-3-030-01440-7_44&partnerID=40&md5=bba797a117cea58f17fce9d057e445c5 Ali, Y. and Padmanabhan, E. and Andriamihaja, S. and Faisal, A. (2019) Spatial variations prediction in carbonate porosity using artificial neural network: Subis Limestones, Sarawak, Malaysia. Advances in Science, Technology and Innovation . pp. 189-191. http://eprints.utp.edu.my/23485/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description The estimation and modeling of carbonate porosity is of increasing interest in different aspects of geology. Several models have been developed to visualize the pore network systems of carbonate rocks. However, no modeling tools have been designed to predict changes in pore system resulting from dissolution. Therefore, this paper introduced an algorithm for predicting spatial variations in pore network. Carbonate outcropped samples representing different facies from Subis limestone, Sarawak, of Miocene age were used for this study. Continuous imagery along a 10 cm rock chip was conducted using Micro Computer Tomography (CT) scan imagery. The Artificial Neural Network (ANN) predictive code receives images which were read as a matrix. The images were processed using the Image Analysis, coded before use as a training and input data set for ANN. The ANN produced a predicted image with the same properties (such as bits, scalar or raster etc.) as the input images and at the same interval. The predicted image was compared to the original one to estimate the prediction accuracy. The method proved to give good results in terms of the predicted images accuracy. The method can be applied to study the dissolution phenomenon in carbonates as well as siliciclastic rocks to predict spatial variations and development in a pore network system. © Springer Nature Switzerland AG 2019.
format Article
author Ali, Y.
Padmanabhan, E.
Andriamihaja, S.
Faisal, A.
spellingShingle Ali, Y.
Padmanabhan, E.
Andriamihaja, S.
Faisal, A.
Spatial variations prediction in carbonate porosity using artificial neural network: Subis Limestones, Sarawak, Malaysia
author_facet Ali, Y.
Padmanabhan, E.
Andriamihaja, S.
Faisal, A.
author_sort Ali, Y.
title Spatial variations prediction in carbonate porosity using artificial neural network: Subis Limestones, Sarawak, Malaysia
title_short Spatial variations prediction in carbonate porosity using artificial neural network: Subis Limestones, Sarawak, Malaysia
title_full Spatial variations prediction in carbonate porosity using artificial neural network: Subis Limestones, Sarawak, Malaysia
title_fullStr Spatial variations prediction in carbonate porosity using artificial neural network: Subis Limestones, Sarawak, Malaysia
title_full_unstemmed Spatial variations prediction in carbonate porosity using artificial neural network: Subis Limestones, Sarawak, Malaysia
title_sort spatial variations prediction in carbonate porosity using artificial neural network: subis limestones, sarawak, malaysia
publisher Springer Nature
publishDate 2019
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108113955&doi=10.1007%2f978-3-030-01440-7_44&partnerID=40&md5=bba797a117cea58f17fce9d057e445c5
http://eprints.utp.edu.my/23485/
_version_ 1738656478756077568
score 13.211869

Similar Items